Stability_Score: Stability score function for (S)MERF and (S)REEMforest...
In sistm/LongituRF: Random Forests for Longitudinal Data

Stability_Score

R Documentation

Stability score function for (S)MERF and (S)REEMforest methods

Description

Computes the stability scores for (S)MERF and (S)REEMforest methods.

Usage

Stability_Score(
  X,
  Y,
  Z,
  id,
  time,
  mtry,
  ntree,
  sto = "BM",
  method = "MERF",
  eta = c(1:ncol(X)),
  nvars = c(1:ncol(X))
)

Arguments

`X`	[matrix]: A `N`x`p` matrix containing the `p` predictors of the fixed effects, column codes for a predictor.
`Y`	[vector]: A vector containing the output trajectories.
`Z`	[matrix]: A `N`x`q` matrix containing the `q` predictor of the random effects.
`id`	[vector]: Is the vector of the identifiers for the different trajectories.
`time`	[vector]: Is the vector of the measurement times associated with the trajectories in `Y`,`Z` and `X`.
`mtry`	[numeric]: Number of variables ramdomly picked to split each node.
`ntree`	[numeric]: Number of trees in the RF.
`sto`	[string]: Defines the covariance function of the stochastic process, can be either `"none"` for no stochastic process, `"BM"` for Brownian motion, `OrnUhl` for standard Ornstein-Uhlenbeck process, `BBridge` for Brownian Bridge, `fbm` for Fractional Brownian motion; can also be a function defined by the user.
`method`	[string]: Defines the method to be used, can be either "MERF" or "REEMforest".
`eta`	[numeric]: The size of the neighborhood for the stability score. Can be a vector, in this case, returns the stability scores corresponding to all the values of the vector.
`nvars`	[numeric]: The number of variables to consider among the most impotant variables. Can be a vector, in this case, the function returns the stability scores corresponding to all the values of the vector.

Value

A matrix with all the stability scores corresponding to the eta and nvars values. The $i$th row corresponds to the $i$th value of eta while the $i$th column corresponds to the $i$ value of nvars.

sistm/LongituRF documentation built on May 23, 2022, 4:25 p.m.